© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30056
    Prev
    Next
    INDEX
    Explanations

    delivery of services, information, or goods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iminal
    -0.10
    illas
    -0.09
    cip
    -0.09
    èģĶç½ij
    -0.09
     ÑĢолÑĮ
    -0.09
    lessly
    -0.09
    ming
    -0.09
    èijŃ
    -0.09
    ifying
    -0.09
    bing
    -0.08
    POSITIVE LOGITS
    æĸ¹å¼ı
    0.09
    åĿļ
    0.09
    umes
    0.09
    è¿ĩç¨ĭä¸Ń
    0.09
    via
    0.08
    åķ
    0.08
    è¡¿
    0.08
    ä½ĵ系建设
    0.08
    缸åĬ©
    0.08
    gov
    0.08
    Activations Density 0.051%

    No Known Activations